© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63776
    Prev
    Next
    INDEX
    Explanations

    errors and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。
    0.41
    ဆင့်
    0.41
    မည်
    0.40
    ēng
    0.39
     woon
    0.39
    ۔
    0.38
     Rainfall
    0.37
     resignation
    0.37
     sådan
    0.36
     င
    0.36
    POSITIVE LOGITS
    Loc
    0.44
    Vari
    0.44
     оборо
    0.44
    在美国
    0.42
    ewood
    0.39
    Quelle
    0.39
    ார்க்க
    0.39
    ете
    0.39
    个人的
    0.38
    Topic
    0.38
    Activations Density 0.005%

    No Known Activations